Machine Learning-Driven Identification of Molecular Subgroups in Medulloblastoma via Gene Expression Profiling.

in Clinical oncology (Royal College of Radiologists (Great Britain)) by H Hourfar, P Taklifi, M Razavi, B Khorsand

TLDR

  • This study demonstrates the use of machine learning algorithms to classify pediatric medulloblastoma subgroups based on gene expression profiles, achieving high classification accuracy and highlighting the potential for personalized treatment strategies.

Abstract

Medulloblastoma (MB) is the most prevalent malignant brain tumour in children, characterised by substantial molecular heterogeneity across its subgroups. Accurate classification is pivotal for personalised treatment strategies and prognostic assessments. In this study, we aimed to build machine learning models to classify MB subgroups. This study utilised machine learning (ML) techniques to analyse RNA sequencing data from 70 paediatric MB samples. Five classifiers-K-nearest neighbors (KNN), decision tree (DT), support vector machine (SVM), random forest (RF), and naive Bayes (NB)-were used to predict molecular subgroups based on gene expression profiles. Feature selection identified gene subsets of varying sizes (750, 75, and 25 genes) to optimise classification accuracy. Initial analyses with the complete gene set lacked discriminative power. However, reduced feature sets significantly enhanced clustering and classification performance, particularly for group 3 and group 4 subgroups. The RF, KNN, and SVM classifiers consistently outperformed the DT and NB classifiers, achieving classification accuracies exceeding 90% in many scenarios, especially in group 3 and group 4 subgroups. This study highlights the efficacy of ML algorithms in classifying MB subgroups using gene expression data. The integration of feature selection techniques substantially improves model performance, paving the way for enhanced personalised approaches in MB management.

Overview

  • Study objective: Build machine learning models to classify medulloblastoma (MB) subgroups based on RNA sequencing data.
  • Methodology: Utilized machine learning techniques to analyze RNA sequencing data from 70 pediatric MB samples; five classifiers were used to predict molecular subgroups based on gene expression profiles.
  • Primary objective: Accurate classification of MB subgroups is crucial for personalized treatment strategies and prognostic assessments.

Comparative Analysis & Findings

  • Five classifiers (KNN, DT, SVM, RF, and NB) were used to predict molecular subgroups based on gene expression profiles; feature selection identified gene subsets of varying sizes to optimize classification accuracy.
  • Reduced feature sets significantly enhanced clustering and classification performance, particularly for group 3 and group 4 subgroups.
  • Random forest, KNN, and SVM classifiers consistently outperformed the other classifiers, achieving classification accuracies exceeding 90% in many scenarios.

Implications and Future Directions

  • The study highlights the efficacy of machine learning algorithms in classifying MB subgroups using gene expression data.
  • Integration of feature selection techniques substantially improves model performance, paving the way for enhanced personalized approaches in MB management.
  • Future studies can explore the application of these machine learning models to other paediatric brain tumour types and potentially integrate additional molecular data, such as genotyping and proteomics, to further enhance classification accuracy.
Read Full Article